Classifying insect pests from image data using deep learning

Abstract

The fact that insecticidal pests impair significant agricultural productivity has become one of the main challenges in agriculture. There are, nevertheless, several requirements for a high-performing automated system that can detect pest insects from vast amounts of visual data. We employed deep learning approaches to correctly identify insect species from large volumes of data in this study model and explainable AI to decide which part of the photos is used to categorize the insects from the data. We chose to deal with the large-scale IP102 dataset since we worked with a large dataset. There are almost 75,000 pictures in this collection, divided into 102 categories. We ran state-of-the-art tests on the unique IP102 data set to evaluate our proposed solution. We used five different Deep Neural Networks (DNN) models for image classification: VGG19, ResNet50, EfficientNetB5, DenseNet121, InceptionV3, and implemented the LIME-based XAI (Explainable Artificial Intelligence) framework. DenseNet121 performed best across all classes, and it was also employed to detect crop-specific insect species. The classification accuracy for eight specific crops ranged from 46.31% to 95.36%. Moreover, we have compared our prediction performance to that of earlier articles to assess the efficacy of our research.